Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    standard template

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    luğ
    1.63
     следует
    1.62
    ፂ
    1.58
    洸
    1.58
    1.58
     इसलिये
    1.57
    städ
    1.52
    𒆷
    1.51
    িশালী
    1.49
     endExpNow
    1.49
    POSITIVE LOGITS
    alities
    2.25
    efined
    2.02
    ist
    1.95
    ising
    1.91
    {
    1.88
    ality
    1.87
    ishes
    1.81
    ization
    1.79
    isation
    1.74
    ade
    1.73
    Act Density 0.663%

    No Known Activations